© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11936
    Prev
    Next
    INDEX
    Explanations

    words that evoke fear or the feeling of being afraid

    oai_token-act-pair · gemini-2.0-flash

    Fear, tax evasion, religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FunctionFlags
    -0.55
    脚注の使い方
    -0.54
    Hochspringen
    -0.52
    IsContent
    -0.51
     applau
    -0.50
     agrade
    -0.49
     Marconi
    -0.49
     SqlDbType
    -0.48
     passione
    -0.47
    ]),
    -0.47
    POSITIVE LOGITS
     Fear
    0.93
     fears
    0.90
     FEAR
    0.88
     fear
    0.87
    fear
    0.85
    Fear
    0.84
     scared
    0.83
     scare
    0.82
     Afraid
    0.81
     phobia
    0.80
    Activations Density 0.418%

    No Known Activations